ORNL engineer uses deep learning to model river temperatures

Sean Turner at Oak Ridge National Laboratory is developing national-scale hydrology models using large-sample deep learning to simulate river temperatures and to couple river models with power grid operations.

• Main action: Turner is creating national-scale hydrology models that use large-sample deep learning to simulate river temperature and behavior across 2.7 million stream reaches in the lower 48 states, despite limited observations (~300 long-duration river temperature records; 2 river reaches in Tennessee). He joined ORNL in 2023 and is developing tools to link river models with power grid operations to support scheduling of hydropower resources.
• Background and details: Turner applies experience from United Utilities, PNNL, and the Joint Global Change Research Institute; the work uses ORNL supercomputing resources and aims to support decisions including siting for small modular nuclear reactors and data centers, and operational planning with the Tennessee Valley Authority.